Search

Start Over Subject function approximation

1. A learning algorithm for a novel neural network architecture motivated by integrate-and-fire neuron model

Creator:
Mishra, Deepak, Yadav, Abhishek, and Kalra, Prem K.
Format:
bez média and svazek
Type:
model:article and TEXT
Subject:
Integrate-And-Fire Neuron Model, function approximation, classification, artificial neural network, and steepest descent method
Language:
English
Description:
In this paper, a learning algorithm for a novel neural network architecture motivated by Integrate-and-Fire Neuron Model (IFN) is proposed and tested for various applications where a multilayer perceptron (MLP) neural network is conventionally used. It is observed that inclusion of a few more biological phenomenon in the formulation of artificial neural networks make them more prevailing. Several benchmark and real-life problems of classification and function-approximation are illustrated.
Rights:
http://creativecommons.org/publicdomain/mark/1.0/ and policy:public